Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Improved Architectures and Training Algorithms for Deep Operator Networks

Journal Article · · Journal of Scientific Computing

Not provided.

Research Organization:
Raytheon Technologies Corp., Waltham, MA (United States); Univ. of Pennsylvania, Philadelphia, PA (United States)
Sponsoring Organization:
USDOE Advanced Research Projects Agency - Energy (ARPA-E)
DOE Contract Number:
AR0001201; SC0019116
OSTI ID:
1976690
Journal Information:
Journal of Scientific Computing, Vol. 92, Issue 2; ISSN 0885-7474
Publisher:
Springer
Country of Publication:
United States
Language:
English

References (17)

Error estimates for DeepONets: a deep learning framework in infinite dimensions journal March 2022
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators journal March 2021
Learning the solution operator of parametric partial differential equations with physics-informed DeepONets journal October 2021
Deep Residual Learning for Image Recognition conference June 2016
Efficient BackProp book January 2012
Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks journal January 2021
Deep learning of free boundary and Stefan problems journal March 2021
Wide neural networks of any depth evolve as linear models under gradient descent * journal December 2020
On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks journal October 2021
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems journal July 1995
DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks journal July 2021
A First Course in the Numerical Analysis of Differential Equations book January 2008
Exponential Time Differencing for Stiff Systems journal March 2002
On the Convergence of Physics Informed Neural Networks for Linear Second-Order Elliptic and Parabolic Type PDEs journal June 2020
Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs journal June 2021
dolfin-adjoint 2018.1: automated adjoints for FEniCS and Firedrake journal June 2019
Array programming with NumPy journal September 2020

Similar Records

Improved Architectures and Training Algorithms for Deep Operator Networks
Journal Article · 2022 · Journal of Scientific Computing · OSTI ID:2339531

Scalable uncertainty quantification for deep operator networks using randomized priors
Journal Article · 2022 · Computer Methods in Applied Mechanics and Engineering · OSTI ID:2339527

Scalable uncertainty quantification for deep operator networks using randomized priors
Journal Article · 2022 · Computer Methods in Applied Mechanics and Engineering · OSTI ID:1976978

Related Subjects